Environmental Machine Learning Strategy in Equities
Log in to collectAcademic paper
Environmental Standards and Stock Returns
William O. Brown; Xiaoli Gao; Yufeng Han; Dayong Huang; Fang Wang
- University of North Carolina at Greensboro
- ?University of North Carolina (UNC) at Greensboro
- University of North Carolina at Charlotte
- ?University of North Carolina (UNC) at Charlotte - Finance
- ?University of North Carolina (UNC) at Greensboro - Bryan School of Business & Economics
- Central Washington University
- ?Central Washington University - College of Business
Strategy in a nutshell
The strategy uses ESG-related data from Refinitiv, filters out incomplete records, and applies Random Forest machine learning to predict monthly stock returns. Portfolios are built by longing high-return predictions and shorting low-return ones.
Economic rationale
Machine learning captures the hidden impact of detailed environmental indicators on stock performance better than aggregate ESG scores. This enhances predictive power and strengthens the link between sustainability and future returns.
Backtest performance
Annualised return16.08%
Volatility12.86%
Sharpe ratio1.25